The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted data from external websites (HTML links and sitemaps) to perform site mapping. This creates a surface for indirect prompt injection where an attacker-controlled website could include malicious instructions intended to influence the agent's behavior.
Ingestion points: External website URLs and sitemap files provided to the crw map tool.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate discovered URLs from the agent's instructions.
Capability inventory: The skill utilizes crw and curl for network discovery and API interaction.
Sanitization: No explicit sanitization or filtering of the discovered URL strings is mentioned in the documentation.
[COMMAND_EXECUTION]: The skill uses the crw command-line utility to perform link extraction and site mapping. It also documents the use of curl for interacting with a REST API using environment variables for authentication, which is a standard and safe practice for API integration.

crw-map